Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     artery
    -0.07
     perfectly
    -0.07
     tighten
    -0.07
    Pool
    -0.07
    View
    -0.06
    -leading
    -0.06
    Revision
    -0.06
    设备
    -0.06
    adients
    -0.06
    loh
    -0.06
    POSITIVE LOGITS
     �
    0.07
     Byz
    0.07
     조사
    0.07
     plusieurs
    0.06
    Continuous
    0.06
    /components
    0.06
     स
    0.06
    �
    0.06
    pret
    0.06
    ヴァ
    0.06
    Act Density 0.093%

    No Known Activations